High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF

Sang, Lu; Hafner, Bjorn; Zuo, Xingxing; Cremers, Daniel

doi:10.1109/wacv56688.2023.00312

Cited by 7 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…General equation for photometric stereo: Depth priors [24], [84] -Definition and collection of priors, computational complexity Masking methods [44], [45], [58] Uniform colour or limited colour variation Lack of robustness and generality, soft specularities Neural networks [9], [34], [68] -Lack of a well-defined BRDF, explainability and various special cases Hybrid models [22], [38], [53], [59] Surface reflection models…”

Section: Photometric Stereomentioning

confidence: 99%

“…For a multi-spectral setting, thus accounting for wavelength as well, there is a study by Lv et al [42]. More such studies can be expected to come in near future, as similar ideas are used for the purpose of object reconstruction by Chen et al [7] and Sang et al [59], while Iwaguchi and Kawasaki [30] optimize the training phase of photometric stereo using DNNs.…”

Section: Computationally Costly Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Non-Lambertian surfaces and their challenges for visual SLAM

Pyykölä,

Joswig,

Ruotsalainen

2023

Preprint

View full text Add to dashboard Cite

Non-Lambertian surfaces are special surfaces that can cause specific type of reflectances called specularities. These specularities pose a potential issue in industrial SLAM, where non-Lambertian surfaces are aplenty naturally, as specularities can violate two common and basic assumptions of computer vision, namely the brightness and colour constancies, which assume that the brightness and colour of same real-world points stays constant across images. The performance of industrial navigation systems can as such be hindered by specularities. This paper reviews fundamental surface reflectance models, modern state-of-the-art computer vision algorithms and two public datasets, KITTI and DiLiGenT, related to non-Lambertian surfaces' research. A new dataset, SPINS, is presented for the purpose of studying non-Lambertian surfaces in navigation and an empirical performance evaluation with ORB SLAM 3 is performed on the data. The paper concludes with discussion about the results of empirical evaluation and the findings of the survey.

show abstract